© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7908
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on CSS numeric literals—especially floating-point values (decimal numbers) used in style declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incorporation
    -0.06
    -ion
    -0.06
    >Title
    -0.06
     vznik
    -0.06
    -men
    -0.06
    -service
    -0.06
     synthesis
    -0.06
    щим
    -0.05
    sal
    -0.05
    ￣｀
    -0.05
    POSITIVE LOGITS
     """↵↵
    0.07
     років
    0.06
    рус
    0.06
    eresa
    0.06
     doubted
    0.06
     şar
    0.06
     COMMON
    0.06
    =cut
    0.06
    andid
    0.06
    긴
    0.06
    Activations Density 0.002%

    No Known Activations